def testMLAlgorithms(project, dates, algorithm):
"""
测试算法接口，把流程相似的算法统一
algorithm : svm, dt, rf
"""
recommendNum = 5 # 推荐数量
excelName = f'output{algorithm}.xlsx'
sheetName = 'result'
"""初始化excel文件"""
ExcelHelper().initExcelFile(fileName=excelName, sheetName=sheetName, excel_key_list=['训练集', '测试集'])
for date in dates:
startTime = datetime.now()
"""直接读取不带路径的信息"""
filename = projectConfig.getRootPath() + os.sep + 'data' + os.sep + 'train' + os.sep + \
f'ML_{project}_data_{date[0]}_{date[1]}_to_{date[2]}_{date[3]}.tsv'
df = pandasHelper.readTSVFile(filename, pandasHelper.INT_READ_FILE_WITHOUT_HEAD)
print("raw df:", df.shape)
# """读取带路径的文件信息"""
# filename = projectConfig.getRootPath() + os.sep + r'data' + os.sep + 'train' + os.sep + \
# f'ML_{project}_data_{date[0]}_{date[1]}_to_{date[2]}_{date[3]}_include_filepath.csv'
# df = pandasHelper.readTSVFile(filename, pandasHelper.INT_READ_FILE_WITH_HEAD,
# sep=StringKeyUtils.STR_SPLIT_SEP_CSV)
"""df做预处理"""
train_data, train_data_y, test_data, test_data_y = MLTrain.preProcessForSingleLabel(df, date, project,
isNOR=True)
recommendList = None
answerList = None
"""根据算法获得推荐列表"""
if algorithm == StringKeyUtils.STR_ALGORITHM_SVM: # 支持向量机
recommendList, answerList = MLTrain.RecommendBySVM(train_data, train_data_y, test_data,
test_data_y, recommendNum=recommendNum)
elif algorithm == StringKeyUtils.STR_ALGORITHM_DT: # 决策树
recommendList, answerList = MLTrain.RecommendByDecisionTree(train_data, train_data_y, test_data,
test_data_y, recommendNum=recommendNum)
elif algorithm == StringKeyUtils.STR_ALGORITHM_RF: # 随机森林
recommendList, answerList = MLTrain.RecommendByRandomForest(train_data, train_data_y, test_data,
test_data_y, recommendNum=recommendNum)
"""根据推荐列表做评价"""
topk, mrr = DataProcessUtils.judgeRecommend(recommendList, answerList, recommendNum)
"""结果写入excel"""
DataProcessUtils.saveResult(excelName, sheetName, topk, mrr, date)
"""文件分割"""
content = ['']
ExcelHelper().appendExcelRow(excelName, sheetName, content, style=ExcelHelper.getNormalStyle())
content = ['训练集', '测试集']
ExcelHelper().appendExcelRow(excelName, sheetName, content, style=ExcelHelper.getNormalStyle())
print("cost time:", datetime.now() - startTime)
def getCommentsForProject(self, owner, repo , limit = -1):
ExcelHelper().initExcelFile(projectConfig.getTestoutputExcelPath(), projectConfig.TEST_OUT_PUT_SHEET_NAME)
helper = ApiHelper(owner=owner, repo=repo)
helper.setAuthorization(True)
#获取项目pullrequest的数量
#requestNumber = helper.getTotalPullRequestNumberForProject()
requestNumber = helper.getMaxSolvedPullRequestNumberForProject()
print("total pull request number:",requestNumber)
language = helper.getLanguageForProject()
print("project language:",language)
resNumber = requestNumber
rr = 0
usefulRequestNumber = 0
commentNumber = 0
while(resNumber > 0):
print("pull request:",resNumber, " now:",rr)
comments = helper.getCommentsForPullRequest(resNumber)
if(comments.__len__()>0):
usefulRequestNumber = usefulRequestNumber + 1
for comment in comments:
self.writeRawCommmentIntoExcel(comment,repo,language)
commentNumber = commentNumber + 1
resNumber = resNumber - 1
rr = rr + 1
if(limit > 0 and rr> limit):
break
self.commentDesensitization()
print("useful pull request:",usefulRequestNumber," total comment:", commentNumber)
def testEARECAlgorithm(project, dates, filter_train=False, filter_test=False, a=0.5):
"""整合 训练数据"""
recommendNum = 5 # 推荐数量
excelName = f'outputEAREC_{project}_{filter_train}_{filter_test}.xls'
sheetName = 'result'
"""计算累积数据"""
topks = []
mrrs = []
precisionks = []
recallks = []
fmeasureks = []
"""初始化excel文件"""
ExcelHelper().initExcelFile(fileName=excelName, sheetName=sheetName, excel_key_list=['训练集', '测试集'])
for date in dates:
startTime = datetime.now()
recommendList, answerList, prList, convertDict, trainSize = EARECTrain.algorithmBody(date, project,
recommendNum,
filter_train=filter_train,
filter_test=filter_test,
a=a)
"""根据推荐列表做评价"""
topk, mrr, precisionk, recallk, fmeasurek = \
DataProcessUtils.judgeRecommend(recommendList, answerList, recommendNum)
topks.append(topk)
mrrs.append(mrr)
precisionks.append(precisionk)
recallks.append(recallk)
fmeasureks.append(fmeasurek)
"""结果写入excel"""
DataProcessUtils.saveResult(excelName, sheetName, topk, mrr, precisionk, recallk, fmeasurek, date)
"""文件分割"""
content = ['']
ExcelHelper().appendExcelRow(excelName, sheetName, content, style=ExcelHelper.getNormalStyle())
content = ['训练集', '测试集']
ExcelHelper().appendExcelRow(excelName, sheetName, content, style=ExcelHelper.getNormalStyle())
print("cost time:", datetime.now() - startTime)
"""计算历史累积数据"""
DataProcessUtils.saveFinallyResult(excelName, sheetName, topks, mrrs, precisionks, recallks,
fmeasureks)
def testBayesAlgorithms(project, dates): # 输入测试日期和对应文件序列 输出一整个算法的表现
recommendNum = 5 # 推荐数量
excelName = 'outputNB.xlsx'
sheetName = 'result'
"""初始化excel文件"""
ExcelHelper().initExcelFile(fileName=excelName, sheetName=sheetName, excel_key_list=['训练集', '测试集'])
for i in range(1, 4): # Bayes 有三个模型
for date in dates:
filename = projectConfig.getRootPath() + r'\data\train' + r'\\' \
+ f'ML_{project}_data_{date[0]}_{date[1]}_to_{date[2]}_{date[3]}.tsv'
df = pandasHelper.readTSVFile(filename, pandasHelper.INT_READ_FILE_WITHOUT_HEAD)
"""df做预处理"""
isNOR = True
if i == 1 or i == 3:
isNOR = False # 对伯努利不做归一
train_data, train_data_y, test_data, test_data_y = MLTrain.preProcessForSingleLabel(df, date, project,
isNOR=isNOR)
"""根据算法获得推荐列表"""
recommendList, answerList = MLTrain.RecommendByNativeBayes(train_data, train_data_y, test_data,
test_data_y, recommendNum, i)
"""根据推荐列表做评价"""
topk, mrr = DataProcessUtils.judgeRecommend(recommendList, answerList, recommendNum)
"""结果写入excel"""
DataProcessUtils.saveResult(excelName, sheetName, topk, mrr, date)
"""文件分割"""
content = ['']
ExcelHelper().appendExcelRow(excelName, sheetName, content, style=ExcelHelper.getNormalStyle())
content = ['训练集', '测试集']
ExcelHelper().appendExcelRow(excelName, sheetName, content, style=ExcelHelper.getNormalStyle())
def writeRawCommmentIntoExcel(self,comment,repo,language):
dataList = []
dataList.append(repo)
dataList.append(comment.path)
dataList.append(language)
dataList.append(comment.body)
dataList.append(comment.userId)
dataList.append(datetime.strptime(comment.createTime,ExcelHelper.STR_STYLE_DATA_DATE))
dataList.append(comment.line)
styleList = [ExcelHelper.getNormalStyle(), ExcelHelper.getNormalStyle(),ExcelHelper.getNormalStyle(),
ExcelHelper.getNormalStyle(), ExcelHelper.getNormalStyle(),ExcelHelper.getDateStyle(),
ExcelHelper.getNormalStyle()]
ExcelHelper().appendExcelRowWithDiffStyle(projectConfig.getTestoutputExcelPath(), projectConfig.TEST_OUT_PUT_SHEET_NAME
, dataList, styleList)
print(dataList)
def testCAAlgorithm(project, dates): # 多个case, 元组代表总共的时间跨度,最后一个月用于测试
"""
algorithm : 基于用户聚类
"""
recommendNum = 5 # 推荐数量
excelName = f'outputCA.xlsx'
sheetName = 'result'
"""初始化excel文件"""
ExcelHelper().initExcelFile(fileName=excelName, sheetName=sheetName, excel_key_list=['训练集', '测试集'])
for date in dates:
startTime = datetime.now()
"""根据推荐列表做评价"""
CATrain.algorithmBody(date, project, recommendNum)
def testAlgorithm(project, dates, filter_train=False, filter_test=False, error_analysis=False,
test_type=StringKeyUtils.STR_TEST_TYPE_SLIDE): # 多个case, 元组代表总共的时间跨度,最后一个月用于测试
"""
algorithm : 基于信息检索
"""
recommendNum = 5 # 推荐数量
excelName = f'outputIR_AC_{project}_{filter_train}_{filter_test}_{error_analysis}.xlsx'
sheetName = 'result'
"""计算累积数据"""
topks = []
mrrs = []
precisionks = []
recallks = []
fmeasureks = []
recommend_positive_success_pr_ratios = [] # pr 中有推荐成功人选的比例
recommend_positive_success_time_ratios = [] # 推荐pr * 人次 中有推荐成功人选的频次比例
recommend_negative_success_pr_ratios = [] # pr 中有推荐人选Hit 但被滤掉的pr的比例
recommend_negative_success_time_ratios = [] # 推荐pr * 人次中有推荐人选Hit 但是被滤掉的pr的比例
recommend_positive_fail_pr_ratios = [] # pr 中有推荐人选推荐错误的pr比例
recommend_positive_fail_time_ratios = [] # pr 中有pr * 人次有推荐错误的频次比例
recommend_negative_fail_pr_ratios = [] # pr 中有推荐人选不知道是否正确的比例
recommend_negative_fail_time_ratios = [] # pr中有pr * 人次有不知道是否正确的比例
error_analysis_datas = None
"""初始化excel文件"""
ExcelHelper().initExcelFile(fileName=excelName, sheetName=sheetName, excel_key_list=['训练集', '测试集'])
for date in dates:
startTime = datetime.now()
"""根据推荐列表做评价"""
recommendList, answerList, prList, convertDict, trainSize = IR_ACTrain.algorithmBody(date, project,
recommendNum,
filter_train=filter_train,
filter_test=filter_test,
test_type=test_type)
topk, mrr, precisionk, recallk, fmeasurek = \
DataProcessUtils.judgeRecommend(recommendList, answerList, recommendNum)
topks.append(topk)
mrrs.append(mrr)
precisionks.append(precisionk)
recallks.append(recallk)
fmeasureks.append(fmeasurek)
error_analysis_data = None
filter_answer_list = None
if error_analysis:
if test_type == StringKeyUtils.STR_TEST_TYPE_SLIDE:
y = date[2]
m = date[3]
filename = projectConfig.getIR_ACDataPath() + os.sep + f'IR_AC_ALL_{project}_data_change_trigger_{y}_{m}_to_{y}_{m}.tsv'
filter_answer_list = DataProcessUtils.getAnswerListFromChangeTriggerData(project, date, prList,
convertDict, filename,
'review_user_login',
'pr_number')
elif test_type == StringKeyUtils.STR_TEST_TYPE_INCREMENT:
fileList = []
for i in range(date[0] * 12 + date[1], date[2] * 12 + date[3] + 1): # 拆分的数据做拼接
y = int((i - i % 12) / 12)
m = i % 12
if m == 0:
m = 12
y = y - 1
fileList.append(
projectConfig.getIR_ACDataPath() + os.sep + f'IR_AC_ALL_{project}_data_change_trigger_{y}_{m}_to_{y}_{m}.tsv')
filter_answer_list = DataProcessUtils.getAnswerListFromChangeTriggerDataByIncrement(project, prList,
convertDict,
fileList,
'review_user_login',
'pr_number')
# recommend_positive_success_pr_ratio, recommend_positive_success_time_ratio, recommend_negative_success_pr_ratio, \
# recommend_negative_success_time_ratio, recommend_positive_fail_pr_ratio, recommend_positive_fail_time_ratio, \
# recommend_negative_fail_pr_ratio, recommend_negative_fail_time_ratio = DataProcessUtils.errorAnalysis(
# recommendList, answerList, filter_answer_list, recommendNum)
# error_analysis_data = [recommend_positive_success_pr_ratio, recommend_positive_success_time_ratio,
# recommend_negative_success_pr_ratio, recommend_negative_success_time_ratio,
# recommend_positive_fail_pr_ratio, recommend_positive_fail_time_ratio,
# recommend_negative_fail_pr_ratio, recommend_negative_fail_time_ratio]
recommend_positive_success_pr_ratio, recommend_negative_success_pr_ratio, recommend_positive_fail_pr_ratio, \
recommend_negative_fail_pr_ratio = DataProcessUtils.errorAnalysis(
recommendList, answerList, filter_answer_list, recommendNum)
error_analysis_data = [recommend_positive_success_pr_ratio,
recommend_negative_success_pr_ratio,
recommend_positive_fail_pr_ratio,
recommend_negative_fail_pr_ratio]
# recommend_positive_success_pr_ratios.append(recommend_positive_success_pr_ratio)
# recommend_positive_success_time_ratios.append(recommend_positive_success_time_ratio)
# recommend_negative_success_pr_ratios.append(recommend_negative_success_pr_ratio)
# recommend_negative_success_time_ratios.append(recommend_negative_success_time_ratio)
# recommend_positive_fail_pr_ratios.append(recommend_positive_fail_pr_ratio)
# recommend_positive_fail_time_ratios.append(recommend_positive_fail_time_ratio)
# recommend_negative_fail_pr_ratios.append(recommend_negative_fail_pr_ratio)
# recommend_negative_fail_time_ratios.append(recommend_negative_fail_time_ratio)
recommend_positive_success_pr_ratios.append(recommend_positive_success_pr_ratio)
recommend_negative_success_pr_ratios.append(recommend_negative_success_pr_ratio)
recommend_positive_fail_pr_ratios.append(recommend_positive_fail_pr_ratio)
recommend_negative_fail_pr_ratios.append(recommend_negative_fail_pr_ratio)
if error_analysis_data:
# error_analysis_datas = [recommend_positive_success_pr_ratios, recommend_positive_success_time_ratios,
# recommend_negative_success_pr_ratios, recommend_negative_success_time_ratios,
# recommend_positive_fail_pr_ratios, recommend_positive_fail_time_ratios,
# recommend_negative_fail_pr_ratios, recommend_negative_fail_time_ratios]
error_analysis_datas = [recommend_positive_success_pr_ratios,
recommend_negative_success_pr_ratios,
recommend_positive_fail_pr_ratios,
recommend_negative_fail_pr_ratios]
"""结果写入excel"""
DataProcessUtils.saveResult(excelName, sheetName, topk, mrr, precisionk, recallk, fmeasurek, date)
"""文件分割"""
content = ['']
ExcelHelper().appendExcelRow(excelName, sheetName, content, style=ExcelHelper.getNormalStyle())
content = ['训练集', '测试集']
ExcelHelper().appendExcelRow(excelName, sheetName, content, style=ExcelHelper.getNormalStyle())
print("cost time:", datetime.now() - startTime)
"""推荐错误可视化"""
DataProcessUtils.recommendErrorAnalyzer2(error_analysis_datas, project,
f'IR_AC_{test_type}_{filter_train}_{filter_test}')
"""计算历史累积数据"""
DataProcessUtils.saveFinallyResult(excelName, sheetName, topks, mrrs, precisionks, recallks,
fmeasureks, error_analysis_datas)
def testRF_AAlgorithms(projects, dates, filter_train=False, filter_test=False, error_analysis=True):
"""
RF 算法由于特征和输入无法和ML兼容，单独开一个文件
"""
startTime = datetime.now()
for project in projects:
excelName = f'outputRF_A_{project}_{filter_train}_{filter_test}_{error_analysis}.xlsx'
recommendNum = 5 # 推荐数量
sheetName = 'result'
"""初始化excel文件"""
ExcelHelper().initExcelFile(fileName=excelName, sheetName=sheetName, excel_key_list=['训练集', '测试集'])
"""初始化项目抬头"""
content = ["项目名称：", project]
ExcelHelper().appendExcelRow(excelName, sheetName, content, style=ExcelHelper.getNormalStyle())
ExcelHelper().appendExcelRow(excelName, sheetName, content, style=ExcelHelper.getNormalStyle())
"""计算累积数据"""
topks = []
mrrs = []
precisionks = []
recallks = []
fmeasureks = []
recommend_positive_success_pr_ratios = [] # pr 中有推荐成功人选的比例
recommend_positive_success_time_ratios = [] # 推荐pr * 人次 中有推荐成功人选的频次比例
recommend_negative_success_pr_ratios = [] # pr 中有推荐人选Hit 但被滤掉的pr的比例
recommend_negative_success_time_ratios = [] # 推荐pr * 人次中有推荐人选Hit 但是被滤掉的pr的比例
recommend_positive_fail_pr_ratios = [] # pr 中有推荐人选推荐错误的pr比例
recommend_positive_fail_time_ratios = [] # pr 中有pr * 人次有推荐错误的频次比例
recommend_negative_fail_pr_ratios = [] # pr 中有推荐人选不知道是否正确的比例
recommend_negative_fail_time_ratios = [] # pr中有pr * 人次有不知道是否正确的比例
error_analysis_datas = None
for date in dates:
recommendList, answerList, prList, convertDict, trainSize = RF_ATrain.algorithmBody(date, project,
recommendNum,
filter_train=filter_train,
filter_test=filter_test)
"""根据推荐列表做评价"""
topk, mrr, precisionk, recallk, fmeasurek = \
DataProcessUtils.judgeRecommend(recommendList, answerList, recommendNum)
topks.append(topk)
mrrs.append(mrr)
precisionks.append(precisionk)
recallks.append(recallk)
fmeasureks.append(fmeasurek)
error_analysis_data = None
if error_analysis:
y = date[2]
m = date[3]
filename = projectConfig.getRF_ADataPath() + os.sep + f'RF_A_ALL_{project}_data_change_trigger_{y}_{m}_to_{y}_{m}.tsv'
filter_answer_list = DataProcessUtils.getAnswerListFromChangeTriggerData(project, date,
prList,
convertDict, filename,
'review_user_login',
'pr_number')
# recommend_positive_success_pr_ratio, recommend_positive_success_time_ratio, recommend_negative_success_pr_ratio, \
# recommend_negative_success_time_ratio, recommend_positive_fail_pr_ratio, recommend_positive_fail_time_ratio, \
# recommend_negative_fail_pr_ratio, recommend_negative_fail_time_ratio = DataProcessUtils.errorAnalysis(
# recommendList, answerList, filter_answer_list, recommendNum)
# error_analysis_data = [recommend_positive_success_pr_ratio, recommend_positive_success_time_ratio,
# recommend_negative_success_pr_ratio, recommend_negative_success_time_ratio,
# recommend_positive_fail_pr_ratio, recommend_positive_fail_time_ratio,
# recommend_negative_fail_pr_ratio, recommend_negative_fail_time_ratio]
recommend_positive_success_pr_ratio, recommend_negative_success_pr_ratio, recommend_positive_fail_pr_ratio, \
recommend_negative_fail_pr_ratio = DataProcessUtils.errorAnalysis(
recommendList, answerList, filter_answer_list, recommendNum)
error_analysis_data = [recommend_positive_success_pr_ratio,
recommend_negative_success_pr_ratio,
recommend_positive_fail_pr_ratio,
recommend_negative_fail_pr_ratio]
# recommend_positive_success_pr_ratios.append(recommend_positive_success_pr_ratio)
# recommend_positive_success_time_ratios.append(recommend_positive_success_time_ratio)
# recommend_negative_success_pr_ratios.append(recommend_negative_success_pr_ratio)
# recommend_negative_success_time_ratios.append(recommend_negative_success_time_ratio)
# recommend_positive_fail_pr_ratios.append(recommend_positive_fail_pr_ratio)
# recommend_positive_fail_time_ratios.append(recommend_positive_fail_time_ratio)
# recommend_negative_fail_pr_ratios.append(recommend_negative_fail_pr_ratio)
# recommend_negative_fail_time_ratios.append(recommend_negative_fail_time_ratio)
recommend_positive_success_pr_ratios.append(recommend_positive_success_pr_ratio)
recommend_negative_success_pr_ratios.append(recommend_negative_success_pr_ratio)
recommend_positive_fail_pr_ratios.append(recommend_positive_fail_pr_ratio)
recommend_negative_fail_pr_ratios.append(recommend_negative_fail_pr_ratio)
if error_analysis_data:
# error_analysis_datas = [recommend_positive_success_pr_ratios, recommend_positive_success_time_ratios,
# recommend_negative_success_pr_ratios, recommend_negative_success_time_ratios,
# recommend_positive_fail_pr_ratios, recommend_positive_fail_time_ratios,
# recommend_negative_fail_pr_ratios, recommend_negative_fail_time_ratios]
error_analysis_datas = [recommend_positive_success_pr_ratios,
recommend_negative_success_pr_ratios,
recommend_positive_fail_pr_ratios,
recommend_negative_fail_pr_ratios]
"""结果写入excel"""
DataProcessUtils.saveResult(excelName, sheetName, topk, mrr, precisionk, recallk, fmeasurek, date, error_analysis_data)
"""文件分割"""
content = ['']
ExcelHelper().appendExcelRow(excelName, sheetName, content, style=ExcelHelper.getNormalStyle())
content = ['训练集', '测试集']
ExcelHelper().appendExcelRow(excelName, sheetName, content, style=ExcelHelper.getNormalStyle())
print("cost time:", datetime.now() - startTime)
"""推荐错误可视化"""
DataProcessUtils.recommendErrorAnalyzer2(error_analysis_datas, project, f'RF_{filter_train}_{filter_test}')
"""计算历史累积数据"""
DataProcessUtils.saveFinallyResult(excelName, sheetName, topks, mrrs, precisionks, recallks, fmeasureks,
error_analysis_datas)
def readOutPutFile(project, keys, cid='whole', filter_train=True, filter_test=True):
"""
key表示具体要获取的数据
"""
# 拼接output文件
returns = []
filename = f"outputCN_{project}_{filter_train}_{filter_test}.xls"
for key in keys:
if key == MODULARITY:
modularitys = []
row_idx = 2
row = ExcelHelper().readExcelRow(filename, "result", startRow=row_idx)
while row is not None and modularitys.__len__() < 12:
if key in row:
next_row = ExcelHelper().readExcelRow(filename, "result", startRow=row_idx + 1)
if next_row[1] == cid:
modularitys.append(next_row[4])
row_idx += 18
row = ExcelHelper().readExcelRow(filename, "result", startRow=row_idx)
returns.append(modularitys)
if key == ENTROPY:
entropys = []
row_idx = 2
row = ExcelHelper().readExcelRow(filename, "result", startRow=row_idx)
while row is not None and entropys.__len__() < 12:
if key in row:
next_row = ExcelHelper().readExcelRow(filename, "result", startRow=row_idx + 1)
if next_row[1] == cid:
entropys.append(next_row[5])
row_idx += 18
row = ExcelHelper().readExcelRow(filename, "result", startRow=row_idx)
returns.append(entropys)
if key == SIZE:
sizes = []
row_idx = 2
row = ExcelHelper().readExcelRow(filename, "result", startRow=row_idx)
while row is not None and sizes.__len__() < 12:
if key in row:
next_row = ExcelHelper().readExcelRow(filename, "result", startRow=row_idx + 1)
if next_row[1] == cid:
sizes.append(next_row[2])
row_idx += 18
row = ExcelHelper().readExcelRow(filename, "result", startRow=row_idx)
returns.append(sizes)
if key == TOPK_ACC:
topks = [[], [], []]
row_idx = 4
row = ExcelHelper().readExcelRow(filename, "result", startRow=row_idx)
while row is not None and topks[0].__len__() < 12:
if key in row:
next_row = ExcelHelper().readExcelRow(filename, "result", startRow=row_idx + 2)
topks[0].append(next_row[2])
topks[1].append(next_row[4])
topks[2].append(next_row[6])
row_idx += 18
row = ExcelHelper().readExcelRow(filename, "result", startRow=row_idx)
returns.append(topks)
return returns
def testCBAlgorithmsByMultipleLabels(projects, dates, algorithms):
"""
algorithm : 混合算法，提供算法的排列组合
项目 -> 日期 -> 算法排列组合
每一个项目占一个文件位置 每一个算法组合占一页
"""
recommendNum = 5 # 推荐数量
for project in projects:
excelName = f'outputCB_{project}.xlsx'
sheetName = 'result'
"""初始化excel文件"""
ExcelHelper().initExcelFile(fileName=excelName, sheetName=sheetName, excel_key_list=['训练集', '测试集'])
"""对不同时间做一个综合统计
组合的int -> [[],[]....]
"""
topks = {}
mrrs = {}
precisionks = {}
recallks = {}
fmeasureks = {}
"""初始化"""
for i in range(1, 2 ** algorithms.__len__()):
topks[i] = []
mrrs[i] = []
precisionks[i] = []
recallks[i] = []
fmeasureks[i] = []
for date in dates:
"""获得不同算法的推荐列表，答案和pr列表"""
"""不同算法预处理可能会筛去一些pr pr列表用于做统一"""
prs = []
recommendLists = []
answerLists = []
"""计算不同人之前在训练集review的次数 作为后面综合统计的第二依据"""
reviewerFreq = DataProcessUtils.getReviewerFrequencyDict(project, date)
for algorithm in algorithms:
print(f"project:{project}, date:{date}, algorithm:{algorithm}")
"""根据算法获得推荐列表"""
recommendList, answerList, prList, convertDict, trainSize = CBTrain.algorithmBody(date, project, algorithm,
recommendNum)
# print(recommendList)
print("trainSize:", trainSize)
"""人名还原"""
recommendList, answerList = CBTrain.recoverName(recommendList, answerList, convertDict)
# print(recommendList)
prs.append(prList)
recommendLists.append(recommendList)
answerLists.append(answerList)
"""不同算法按照共有的pr 顺序调整"""
prs, recommendLists, answerLists = CBTrain.normList(prs, recommendLists, answerLists)
"""貌似推荐是人名也可以做效果评估 暂时不转化"""
# CBTrain.convertNameToNumber(recommendLists, answerLists)
"""对不同算法做排列组合"""
for i in range(1, 2 ** algorithms.__len__()):
tempRecommendList = []
"""不同算法测试的 answer列表相同，取一个即可"""
answer = answerLists[0]
involve = [0] * algorithms.__len__()
k = i
for j in range(0, algorithms.__len__()):
involve[algorithms.__len__() - j - 1] = k % 2
k = floor(k / 2)
"""组合算法label为excel sheetName"""
label = ''
for j in range(0, algorithms.__len__()):
if involve[j] == 1:
if label != '':
label = label + '_'
label = label + algorithms[j]
tempRecommendList.append(recommendLists[j])
sheetName = label
ExcelHelper().addSheet(filename=excelName, sheetName=sheetName)
"""波达计数 结合不同投票选出最终名单"""
finalRecommendList = []
for j in range(0, answer.__len__()):
recommendList = SortAlgorithmUtils.BordaCountSortWithFreq([x[j] for x in tempRecommendList],
reviewerFreq)
finalRecommendList.append(recommendList)
"""评价指标"""
topk, mrr, precisionk, recallk, fmeasurek = \
DataProcessUtils.judgeRecommend(finalRecommendList, answer, recommendNum)
"""结果写入excel"""
DataProcessUtils.saveResult(excelName, sheetName, topk, mrr, precisionk, recallk, fmeasurek, date)
"""累积评价指标"""
topks[i].append(topk)
mrrs[i].append(mrr)
precisionks[i].append(precisionk)
recallks[i].append(recallk)
fmeasureks[i].append(fmeasurek)
"""对指标做综合评判"""
for i in range(1, 2 ** algorithms.__len__()):
involve = [0] * algorithms.__len__()
k = i
for j in range(0, algorithms.__len__()):
involve[algorithms.__len__() - j - 1] = k % 2
k = floor(k / 2)
"""组合算法label为excel sheetName"""
label = ''
for j in range(0, algorithms.__len__()):
if involve[j] == 1:
if label != '':
label = label + '_'
label = label + algorithms[j]
sheetName = label
DataProcessUtils.saveFinallyResult(excelName, sheetName, topks[i], mrrs[i], precisionks[i], recallks[i],
fmeasureks[i])
def testCNAlgorithm(project, dates, filter_train=False, filter_test=False, is_split=False, error_analysis=False):
"""整合 训练数据"""
"""2020.8.7 新增参数 filter_data 和 error_analysis
filter_train 判断是否使用 changetrigger过滤的训练数据
filter_test 判断是否使用 changetrigger过滤的验证数据
error_analysis 表示是否开启chang_trigger过滤答案的错误统计机制
"""
recommendNum = 5 # 推荐数量
excelName = f'outputCN_{project}_{filter_train}_{filter_test}_{error_analysis}.xlsx'
sheetName = 'result'
"""计算累积数据"""
topks = []
mrrs = []
precisionks = []
recallks = []
fmeasureks = []
recommend_positive_success_pr_ratios = [] # pr 中有推荐成功人选的比例
recommend_positive_success_time_ratios = [] # 推荐pr * 人次 中有推荐成功人选的频次比例
recommend_negative_success_pr_ratios = [] # pr 中有推荐人选Hit 但被滤掉的pr的比例
recommend_negative_success_time_ratios = [] # 推荐pr * 人次中有推荐人选Hit 但是被滤掉的pr的比例
recommend_positive_fail_pr_ratios = [] # pr 中有推荐人选推荐错误的pr比例
recommend_positive_fail_time_ratios = [] # pr 中有pr * 人次有推荐错误的频次比例
recommend_negative_fail_pr_ratios = [] # pr 中有推荐人选不知道是否正确的比例
recommend_negative_fail_time_ratios = [] # pr中有pr * 人次有不知道是否正确的比例
error_analysis_datas = None
"""初始化excel文件"""
ExcelHelper().initExcelFile(fileName=excelName, sheetName=sheetName, excel_key_list=['训练集', '测试集'])
for date in dates:
CNTrain.clean()
startTime = datetime.now()
prList, convertDict, trainSize, communities_data= CNTrain.algorithmBody(date, project,
recommendNum,
filter_train=filter_train,
filter_test=filter_test,
is_split=is_split)
communitiesTuple = sorted(communities_data.items(), key=lambda x: x[0])
for cid, c_data in communitiesTuple:
"""根据推荐列表做评价"""
topk, mrr, precisionk, recallk, fmeasurek = \
DataProcessUtils.judgeRecommend(c_data['recommend_list'], c_data['answer_list'], recommendNum)
communities_data[cid]['topk'] = topk
communities_data[cid]['mrr'] = mrr
communities_data[cid]['precisionk'] = precisionk
communities_data[cid]['recallk'] = recallk
communities_data[cid]['fmeasurek'] = fmeasurek
print("project: {0}, modularity: {1}, entropy: {2}, avg_variance: {3}".format(project,
communities_data['whole']['modularity'],
communities_data['whole']['entropy'],
communities_data['whole']['avg_variance']))
error_analysis_data = None
if error_analysis:
y = date[2]
m = date[3]
filename = projectConfig.getCNDataPath() + os.sep + f'CN_{project}_data_change_trigger_{y}_{m}_to_{y}_{m}.tsv'
filter_answer_list = DataProcessUtils.getAnswerListFromChangeTriggerData(project, date, prList,
convertDict, filename,
'reviewer', 'pull_number')
# recommend_positive_success_pr_ratio, recommend_positive_success_time_ratio, recommend_negative_success_pr_ratio, \
# recommend_negative_success_time_ratio, recommend_positive_fail_pr_ratio, recommend_positive_fail_time_ratio, \
# recommend_negative_fail_pr_ratio, recommend_negative_fail_time_ratio = DataProcessUtils.errorAnalysis(
# recommendList, answerList, filter_answer_list, recommendNum)
# error_analysis_data = [recommend_positive_success_pr_ratio, recommend_positive_success_time_ratio,
# recommend_negative_success_pr_ratio, recommend_negative_success_time_ratio,
# recommend_positive_fail_pr_ratio, recommend_positive_fail_time_ratio,
# recommend_negative_fail_pr_ratio, recommend_negative_fail_time_ratio]
recommend_positive_success_pr_ratio, recommend_negative_success_pr_ratio, recommend_positive_fail_pr_ratio, \
recommend_negative_fail_pr_ratio = DataProcessUtils.errorAnalysis(
communities_data['whole']['recommend_list'], communities_data['whole']['answer_list'], filter_answer_list, recommendNum)
error_analysis_data = [recommend_positive_success_pr_ratio,
recommend_negative_success_pr_ratio,
recommend_positive_fail_pr_ratio,
recommend_negative_fail_pr_ratio]
# recommend_positive_success_pr_ratios.append(recommend_positive_success_pr_ratio)
# recommend_positive_success_time_ratios.append(recommend_positive_success_time_ratio)
# recommend_negative_success_pr_ratios.append(recommend_negative_success_pr_ratio)
# recommend_negative_success_time_ratios.append(recommend_negative_success_time_ratio)
# recommend_positive_fail_pr_ratios.append(recommend_positive_fail_pr_ratio)
# recommend_positive_fail_time_ratios.append(recommend_positive_fail_time_ratio)
# recommend_negative_fail_pr_ratios.append(recommend_negative_fail_pr_ratio)
# recommend_negative_fail_time_ratios.append(recommend_negative_fail_time_ratio)
recommend_positive_success_pr_ratios.append(recommend_positive_success_pr_ratio)
recommend_negative_success_pr_ratios.append(recommend_negative_success_pr_ratio)
recommend_positive_fail_pr_ratios.append(recommend_positive_fail_pr_ratio)
recommend_negative_fail_pr_ratios.append(recommend_negative_fail_pr_ratio)
if error_analysis_data:
# error_analysis_datas = [recommend_positive_success_pr_ratios, recommend_positive_success_time_ratios,
# recommend_negative_success_pr_ratios, recommend_negative_success_time_ratios,
# recommend_positive_fail_pr_ratios, recommend_positive_fail_time_ratios,
# recommend_negative_fail_pr_ratios, recommend_negative_fail_time_ratios]
error_analysis_datas = [recommend_positive_success_pr_ratios,
recommend_negative_success_pr_ratios,
recommend_positive_fail_pr_ratios,
recommend_negative_fail_pr_ratios]
topks.append(communities_data['whole']['topk'])
mrrs.append(communities_data['whole']['mrr'])
precisionks.append(communities_data['whole']['precisionk'])
recallks.append(communities_data['whole']['recallk'])
fmeasureks.append(communities_data['whole']['fmeasurek'])
"""结果写入excel"""
DataProcessUtils.saveResult_Community_Version(excelName, sheetName, communities_data, date)
error_analysis_data = None
if error_analysis:
y = date[2]
m = date[3]
filename = projectConfig.getCNDataPath() + os.sep + f'CN_{project}_data_change_trigger_{y}_{m}_to_{y}_{m}.tsv'
filter_answer_list = DataProcessUtils.getAnswerListFromChangeTriggerData(project, date, prList,
convertDict, filename,
'reviewer', 'pull_number')
# recommend_positive_success_pr_ratio, recommend_positive_success_time_ratio, recommend_negative_success_pr_ratio, \
# recommend_negative_success_time_ratio, recommend_positive_fail_pr_ratio, recommend_positive_fail_time_ratio, \
# recommend_negative_fail_pr_ratio, recommend_negative_fail_time_ratio = DataProcessUtils.errorAnalysis(
# recommendList, answerList, filter_answer_list, recommendNum)
# error_analysis_data = [recommend_positive_success_pr_ratio, recommend_positive_success_time_ratio,
# recommend_negative_success_pr_ratio, recommend_negative_success_time_ratio,
# recommend_positive_fail_pr_ratio, recommend_positive_fail_time_ratio,
# recommend_negative_fail_pr_ratio, recommend_negative_fail_time_ratio]
recommend_positive_success_pr_ratio, recommend_negative_success_pr_ratio, recommend_positive_fail_pr_ratio,\
recommend_negative_fail_pr_ratio = DataProcessUtils.errorAnalysis(
communities_data['whole']['recommend_list'], communities_data['whole']['answer_list']
, filter_answer_list, recommendNum)
error_analysis_data = [recommend_positive_success_pr_ratio,
recommend_negative_success_pr_ratio,
recommend_positive_fail_pr_ratio,
recommend_negative_fail_pr_ratio]
# recommend_positive_success_pr_ratios.append(recommend_positive_success_pr_ratio)
# recommend_positive_success_time_ratios.append(recommend_positive_success_time_ratio)
# recommend_negative_success_pr_ratios.append(recommend_negative_success_pr_ratio)
# recommend_negative_success_time_ratios.append(recommend_negative_success_time_ratio)
# recommend_positive_fail_pr_ratios.append(recommend_positive_fail_pr_ratio)
# recommend_positive_fail_time_ratios.append(recommend_positive_fail_time_ratio)
# recommend_negative_fail_pr_ratios.append(recommend_negative_fail_pr_ratio)
# recommend_negative_fail_time_ratios.append(recommend_negative_fail_time_ratio)
recommend_positive_success_pr_ratios.append(recommend_positive_success_pr_ratio)
recommend_negative_success_pr_ratios.append(recommend_negative_success_pr_ratio)
recommend_positive_fail_pr_ratios.append(recommend_positive_fail_pr_ratio)
recommend_negative_fail_pr_ratios.append(recommend_negative_fail_pr_ratio)
if error_analysis_data:
# error_analysis_datas = [recommend_positive_success_pr_ratios, recommend_positive_success_time_ratios,
# recommend_negative_success_pr_ratios, recommend_negative_success_time_ratios,
# recommend_positive_fail_pr_ratios, recommend_positive_fail_time_ratios,
# recommend_negative_fail_pr_ratios, recommend_negative_fail_time_ratios]
error_analysis_datas = [recommend_positive_success_pr_ratios,
recommend_negative_success_pr_ratios,
recommend_positive_fail_pr_ratios,
recommend_negative_fail_pr_ratios]
"""结果写入excel"""
DataProcessUtils.saveResult(excelName, sheetName, topk, mrr, precisionk, recallk, fmeasurek, date, error_analysis_data)
"""文件分割"""
content = ['']
ExcelHelper().appendExcelRow(excelName, sheetName, content, style=ExcelHelper.getNormalStyle())
content = ['训练集', '测试集']
ExcelHelper().appendExcelRow(excelName, sheetName, content, style=ExcelHelper.getNormalStyle())
print("cost time:", datetime.now() - startTime)
"""推荐错误可视化"""
DataProcessUtils.recommendErrorAnalyzer2(error_analysis_datas, project, f'CN_{filter_train}_{filter_test}')
"""计算历史累积数据"""
DataProcessUtils.saveFinallyResult(excelName, sheetName, topks, mrrs, precisionks, recallks, fmeasureks, error_analysis_datas)
print(reviewer, temp_df.shape[0])
if reviewer not in reviewer_list:
tempDict = {"reviewer": reviewer}
for i in range(date[0] * 12 + date[1], date[2] * 12 + date[3] + 1): # 拆分的数据做拼接
y = int((i - i % 12) / 12)
m = i % 12
if m == 0:
m = 12
y = y - 1
df = temp_df.loc[(temp_df['label_y'] == y) & (temp_df['label_m'] == m)].copy(deep=True)
sum = df.shape[0]
if sum == 0:
pass
# tempDict[f'{y}年{m}月'] = 0
else:
valid = df.loc[df['change_trigger'] >= 0].shape[0]
tempDict[f'{y}年{m}月'] = valid / sum
ratio_df = ratio_df.append(tempDict, ignore_index=True)
print(ratio_df.shape)
# ratio_df.to_excel("q5_change_trigger_ratio.xls")
if __name__ == "__main__":
df = commentAcceptRate.commentAcceptRatioByProject(["tezos"], (2020, 7, 2020, 9))
"""计算的df写入xlsx"""
fileName = "project_index.xlsx"
sheetName = "commentAcceptRatio"
ExcelHelper().writeDataFrameToExcel(fileName, sheetName, df)
def commentDesensitization(self):
for col in self.DesensitizeKeyList:
ExcelHelper().desensitizationExcelCol(projectConfig.getTestoutputExcelPath(), projectConfig.TEST_OUT_PUT_SHEET_NAME\
, col, 1)
